Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 132 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.2253. Min Act: -0.1700

Data Index: 682689 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.2095. Min Act: -0.1700

Data Index: 149784 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.2253. Min Act: -0.1700

Data Index: 731170 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.1938. Min Act: -0.1700

Data Index: 862448 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.2095. Min Act: -0.1700

Data Index: 1352580 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.2253. Min Act: -0.1700

Data Index: 195547 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.2095. Min Act: -0.1700

Data Index: 84114 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.2095. Min Act: -0.1700

Data Index: 1258974 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.2253. Min Act: -0.1700

Data Index: 219244 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.2253. Min Act: -0.1700

Data Index: 94461 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.1938. Min Act: -0.1700

Data Index: 1351416 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.1938. Min Act: -0.1700

Data Index: 301538 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.2095. Min Act: -0.1700

Data Index: 377954 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.1938. Min Act: -0.1700

Data Index: 1110019 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.1938. Min Act: -0.1700

Data Index: 1303419 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.1938. Min Act: -0.1700

Data Index: 480036 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.1781. Min Act: -0.1700

Data Index: 1019111 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.1781. Min Act: -0.1700

Data Index: 379618 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.1781. Min Act: -0.1700

Data Index: 572303 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 3.2253. Min Range: -3.2253

Max Act: 3.1781. Min Act: -0.1700

Data Index: 1291819 (C4 (Web Text))

Max Activating Token Index: 122